Merge remote-tracking branch 'origin/main'

download_video.py

@@ -1,23 +1,37 @@
-from google.colab import files
-import shutil
 import os
+import random
+import shutil
+from concurrent.futures import ThreadPoolExecutor
+from google.colab import files
+
 basepath = os.getcwd()
-uploaded = files.upload() # 上传文件
+uploaded = files.upload()  # 上传文件
 for filename in uploaded.keys():
-    assert(filename.endswith(".txt")), "speaker-videolink info could only be .txt file!"
+    assert (filename.endswith(".txt")), "speaker-videolink info could only be .txt file!"
     shutil.move(os.path.join(basepath, filename), os.path.join("./speaker_links.txt"))
 
-with open("./speaker_links.txt", 'r', encoding='utf-8') as f:
+
-    lines = f.readlines()
+def generate_infos():
-speakers = []
+    infos = []
-for line in lines:
+    with open("./speaker_links.txt", 'r', encoding='utf-8') as f:
-    line = line.replace("\n", "").replace(" ", "")
+        lines = f.readlines()
-    if line == "":
+    for line in lines:
-        continue
+        line = line.replace("\n", "").replace(" ", "")
-    speaker, link = line.split("|")
+        if line == "":
-    if speaker not in speakers:
+            continue
-        speakers.append(speaker)
+        speaker, link = line.split("|")
-    # download link
+        filename = speaker + "_" + str(random.randint(0, 1000000))
-    import random
+        infos.append({"link": link, "filename": filename})
-    filename = speaker + "_" + str(random.randint(0, 1000000))
+    return infos
+
+
+def download_video(info):
+    link = info["link"]
+    filename = info["filename"]
     os.system(f"youtube-dl -f 0 {link} -o ./video_data/{filename}.mp4")
+
+
+if __name__ == "__main__":
+    infos = generate_infos()
+    with ThreadPoolExecutor(max_workers=os.cpu_count()) as executor:
+        executor.map(download_video, infos)

video2audio.py

@@ -1,10 +1,27 @@
-from moviepy.editor import AudioFileClip
 import os
+from concurrent.futures import ThreadPoolExecutor
+
+from moviepy.editor import AudioFileClip
+
 video_dir = "./video_data/"
 audio_dir = "./raw_audio/"
 filelist = list(os.walk(video_dir))[0][2]
-for file in filelist:
-    if file.endswith(".mp4"):
-        my_audio_clip = AudioFileClip(video_dir + file)
-        my_audio_clip.write_audiofile(audio_dir + file.rstrip(".mp4") + ".wav")
 
+
+def generate_infos():
+    videos = []
+    for file in filelist:
+        if file.endswith(".mp4"):
+            videos.append(file)
+    return videos
+
+
+def clip_file(file):
+    my_audio_clip = AudioFileClip(video_dir + file)
+    my_audio_clip.write_audiofile(audio_dir + file.rstrip(".mp4") + ".wav")
+
+
+if __name__ == "__main__":
+    infos = generate_infos()
+    with ThreadPoolExecutor(max_workers=os.cpu_count()) as executor:
+        executor.map(clip_file, infos)